Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix

13 September 2019

Papers citing "Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix"

7 / 7 papers shown

Title
Cartan moving frames and the data manifoldsInformation Geometry (IG), 2024 Eliot Tron Rita Fioresi Nicolas Couellan Stéphane Puechmorel 158 1 0 18 Sep 2024
Model Inversion Attack via Dynamic Memory LearningACM Multimedia (ACM MM), 2023 Gege Qi YueFeng Chen Xiaofeng Mao Binyuan Hui Xiaodan Li Rong Zhang Hui Xue 257 11 0 24 Aug 2023
Adversarial robustness of amortized Bayesian inferenceInternational Conference on Machine Learning (ICML), 2023 Manuel Glöckler Michael Deistler Jakob H. Macke AAML 255 18 0 24 May 2023
Identifying Adversarially Attackable and Robust Samples Vyas Raina Mark Gales AAML 216 3 0 30 Jan 2023
Adaptive Label Smoothing To Regularize Large-Scale Graph TrainingSDM (SDM), 2021 Kaixiong Zhou Ninghao Liu Fan Yang Zirui Liu Rui Chen Li Li Soo-Hyun Choi Helen Zhou AI4CE 142 22 0 30 Aug 2021
Stabilized Medical Image AttacksInternational Conference on Learning Representations (ICLR), 2021 Gege Qi Lijun Gong Yibing Song Kai Ma Yefeng Zheng OOD AAML MedIm 137 34 0 09 Mar 2021
Towards Understanding Label Smoothing Yi Tian Xu Yuanhong Xu Qi Qian Hao Li Rong Jin UQCV 167 47 0 20 Jun 2020